Angular penalty loss functions in Pytorch (ArcFace, SphereFace, Additive Margin, CosFace)
The developer of this repository has not created any items for sale yet. Need a bug fixed? Help with integration? A different license? Create a request here:
Concise Pytorch implementation of the Angular Penalty Softmax Losses presented in:
(Note: the SphereFace implementation is not exactly as described in their paper but instead uses the 'trick' presented in the ArcFace paper to use arccosine instead of the double angle formula)
from loss_functions import AngularPenaltySMLoss
in_features = 512 out_features = 10 # Number of classes
criterion = AngularPenaltySMLoss(in_features, out_features, loss_type='arcface') # loss_type in ['arcface', 'sphereface', 'cosface']
Forward method works similarly to nn.CrossEntropyLoss
x of shape (batch_size, in_features), labels of shape (batch_size,)
labels should indicate class of each sample, and should be an int, l satisying 0 <= l < out_dim
loss = criterion(x, labels) loss.backward()
There are a simple set of experiments on Fashion-MNIST  included in
train_fMNIST.pywhich compares the use of ordinary Softmax and Additive Margin Softmax loss functions by projecting embedding features onto a 3D sphere.
The experiments can be run like so:
python train_fMNIST.py --num-epochs 40 --seed 1234 --use-cuda
Which produces the following results:
TODO: fix sphereface results
 Deng, J. et al. (2018) ‘ArcFace: Additive Angular Margin Loss for Deep Face Recognition’. Available at: http://arxiv.org/abs/1801.07698.
 Liu, W. et al. (2017) ‘SphereFace: Deep hypersphere embedding for face recognition’, in Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, pp. 6738–6746. doi: 10.1109/CVPR.2017.713.
 Wang, H. et al. (2018) ‘CosFace: Large Margin Cosine Loss for Deep Face Recognition’. Available at: http://openaccess.thecvf.com/contentcvpr2018/papers/WangCosFaceLargeMarginCVPR2018paper.pdf (Accessed: 12 August 2019).
 “Additive Margin Softmax for Face Verification.” Wang, Feng, Jian Cheng, Weiyang Liu and Haijun Liu. IEEE Signal Processing Letters 25 (2018): 926-930.
 "Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms." Han Xiao, Kashif Rasul, Roland Vollgraf. arXiv:1708.07747